OcularChat, fine-tuned from Qwen2.5-VL on 705k simulated dialogues, reaches 0.954/0.849/0.678 accuracy on three AMD tasks in AREDS data, beats prior MLLMs, and scores higher than baselines on ophthalmologist grading of reasoning quality.
Development and ValidaMon of a Deep Learning Algorithm for DetecMon of DiabeMc ReMnopathy in ReMnal Fundus Photographs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Multimodal Conversational AI for Age-Related Macular Degeneration
OcularChat, fine-tuned from Qwen2.5-VL on 705k simulated dialogues, reaches 0.954/0.849/0.678 accuracy on three AMD tasks in AREDS data, beats prior MLLMs, and scores higher than baselines on ophthalmologist grading of reasoning quality.